Fed-BioMed, an open source framework for federated learning in real world healthcare applications#

2023 AI4Health practical session#

This practical session focuses on federated learning (FL) for healthcare applications, and is based on Fed-BioMed, an open source framework for deploying FL in real world use-cases. Throughout the session the participants will get introduced to the basics of federated learning, and will learn to deploy a federated training in a network of clients by using the Fed-BioMed software components. We will focus on the federation of general machine learning approaches for the analysis of medical data (such as tabular or medical images), using a variety of AI frameworks, from Pytorch to scikit-learn. Most advanced topics include the use of privacy-preserving techniques in FL, and the definition of custom data types, models and optimisation routines.

Program#

The workshop lasts 6 hours, broken into 4 slots of 1.5 hours each. The program of the workshop is:

  • Introduction to FL and its importance in medical research (slides)

  • Fed-BioMed introduction and MedNIST tutorial (notebook)

  • Hands-on exercise: detecting heart disease from tabular data (notebook)

  • Hands-on exercise: segmentation of brain MRI images (notebook)

Using Fed-BioMed during the workshop#

We provide a ready-to-use JupyterHub server. Follow the instructions to find out how to connect.

Community#

Keep up to date and ask support questions through our mailing list and our user discord channel.

We welcome new contributors! Check out our repo if you are interested.

We are looking for new collaborations! Share your research ideas through our mailing list or get in touch with Francesco directly.